**Job Description**
This postdoctoral associate position at Duke University focuses on scientific machine learning (SciML) as part of an NIH-funded Center for Excellence in Multiscale Immune Systems Modeling. The role involves leveraging and developing new equation learning methods, such as Physics-Informed Neural Networks (PINNs) and Biologically Informed Neural Networks (BINNs), to derive interpretable and computationally efficient differential equation models from multi-cellular agent-based models (ABMs) of Epstein-Barr Virus (EBV) and HIV-1 infection dynamics. The associate will collaborate with experimentalists to utilize infection data and ABM simulations to identify key mechanistic drivers of viral persistence and immune response, developing biologically-constrained machine learning-based model discovery pipelines to derive interpretable surrogate models from simulated ABM data and spatial-omics data.
**Skills & Abilities**
• Proficiency with deep learning frameworks (e.g., PyTorch, TensorFlow, and JAX).
• Experience in PDE/ODE modeling and numerical methods.
• Strong interest in interpretable ML and mechanistic model discovery.
**Qualifications**
Required Degree(s) in:
• Applied Mathematics
• Computational Science
• Statistics
• Machine Learning
• Related quantitative field
Note: We’ve analyzed the actual job post using AI, for more details visit the original job post by clicking on “Apply Now”!
